Sympy
zLanqing/codex-claude-academic-skills
A skill your agent uses when working with symbolic mathematics in Python.
Constructs honest, checkable derivation chains for formulas and theory notes, and keeps approximations and numerical hints from passing as rigorous proof.
SKILL.md written in Chinese; this summary is our English description.
Install Math Derivation Auditor
$ npx skills add tradecatlabs/vibe-coding-cn --skill math-derivation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tradecatlabs/vibe-coding-cn math-derivation --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/tradecatlabs/vibe-coding-cn.git skills-src && mkdir -p .claude/skills && cp -r skills-src/research/vibe-mathing-cn-public/.codex/skills/math-derivation .claude/skills/math-derivation && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "math-derivation" agent skill from https://github.com/tradecatlabs/vibe-coding-cn/tree/develop/research/vibe-mathing-cn-public/.codex/skills/math-derivation into .claude/skills/math-derivation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "math-derivation", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/tradecatlabs/vibe-coding-cn/tree/develop/research/vibe-mathing-cn-public/.codex/skills/math-derivationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add tradecatlabs/vibe-coding-cn --skill math-derivation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tradecatlabs/vibe-coding-cn math-derivation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tradecatlabs/vibe-coding-cn.git skills-src && mkdir -p .agents/skills && cp -r skills-src/research/vibe-mathing-cn-public/.codex/skills/math-derivation .agents/skills/math-derivation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "math-derivation" agent skill from https://github.com/tradecatlabs/vibe-coding-cn/tree/develop/research/vibe-mathing-cn-public/.codex/skills/math-derivation into .agents/skills/math-derivation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "math-derivation", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tradecatlabs/vibe-coding-cn --skill math-derivation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tradecatlabs/vibe-coding-cn math-derivation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tradecatlabs/vibe-coding-cn.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/research/vibe-mathing-cn-public/.codex/skills/math-derivation .cursor/skills/math-derivation && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "math-derivation" agent skill from https://github.com/tradecatlabs/vibe-coding-cn/tree/develop/research/vibe-mathing-cn-public/.codex/skills/math-derivation into .cursor/skills/math-derivation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "math-derivation", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/tradecatlabs/vibe-coding-cn.git --path research/vibe-mathing-cn-public/.codex/skills/math-derivation--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add tradecatlabs/vibe-coding-cn --skill math-derivation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tradecatlabs/vibe-coding-cn math-derivation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tradecatlabs/vibe-coding-cn.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/research/vibe-mathing-cn-public/.codex/skills/math-derivation .gemini/skills/math-derivation && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "math-derivation" agent skill from https://github.com/tradecatlabs/vibe-coding-cn/tree/develop/research/vibe-mathing-cn-public/.codex/skills/math-derivation into .gemini/skills/math-derivation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "math-derivation", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install tradecatlabs/vibe-coding-cn math-derivationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add tradecatlabs/vibe-coding-cn --skill math-derivation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tradecatlabs/vibe-coding-cn.git skills-src && mkdir -p .github/skills && cp -r skills-src/research/vibe-mathing-cn-public/.codex/skills/math-derivation .github/skills/math-derivation && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "math-derivation" agent skill from https://github.com/tradecatlabs/vibe-coding-cn/tree/develop/research/vibe-mathing-cn-public/.codex/skills/math-derivation into .github/skills/math-derivation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "math-derivation", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tradecatlabs/vibe-coding-cn --skill math-derivation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tradecatlabs/vibe-coding-cn math-derivation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tradecatlabs/vibe-coding-cn.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/research/vibe-mathing-cn-public/.codex/skills/math-derivation .opencode/skills/math-derivation && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "math-derivation" agent skill from https://github.com/tradecatlabs/vibe-coding-cn/tree/develop/research/vibe-mathing-cn-public/.codex/skills/math-derivation into .opencode/skills/math-derivation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "math-derivation", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
math-derivation- GitHub stars
- 17k
- Token cost
- ~429 tokens
- SKILL.md length
- 80 words
- Files
- 6 (incl. references)
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- MIT
At a glance
Constructs honest, checkable derivation chains for formulas and theory notes, and keeps approximations and numerical hints from passing as rigorous proof.
- Tidying scattered formulas into one derivation with fixed notation
- SKILL.md covers Position in the Method Map, When to Use This Skill, Not For / Boundaries and Quick Reference, plus 3 more sections
- Calls python3
- Checking a derivation for hidden assumptions, mixed objects or changed limits
What it does
The skill sits between problem specification and formal proof. It keeps the definitions and quantifiers of the problem contract fixed, then breaks the argument into intermediate propositions a reviewer can check. A quick-reference card asks for the target and its role (identity, proposition, approximation or interpretation), the single top-level object carried through the derivation, and all assumptions, whether explicit, hidden, local, asymptotic or regularity conditions.
Boundaries are spelled out. It is not Lean elaboration or an automated solver, so formal proof terms go to `math-formalization`, full theorem proofs to `math-proof`, and symbolic or numeric checks to `math-computation`, whose results count only as evidence. It must not silently add assumptions, swap limits and integrals or ignore convergence. Three examples cover an exact identity, an asymptotic approximation with stated error order and domain, and a case where a local proxy was mistaken for the global target. The text is in Chinese.
When your agent uses it
- Tidying scattered formulas into one derivation with fixed notation
- Checking a derivation for hidden assumptions, mixed objects or changed limits
- Deriving an asymptotic approximation with its domain of validity and error order
Example prompts
- “把这几条散乱的公式整理成一条推导链，并列出所有隐藏假设。”
- “Derive the large-sample approximation in notes/theory.md and state the limit variable, remainder and error order.”
- “Check whether these two algebraic expressions are equivalent and mark how far the check goes.”
Requirements
- SymPy, if you want the symbolic difference-to-zero check for identities
What it can do on your machine
Read from SKILL.md and the folder at commit 0a7fdf4. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Math Derivation Auditor loads about 429 tokens when it runs, and up to ~619 if it reads all its reference files. Until then it costs about 20 tokens; SKILL.md has 80 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from tradecatlabs/vibe-coding-cn at commit 0a7fdf4, republished under its MIT licence (© tradecatlabs). 80 words, ~429 tokens.
Download SKILL.mdSave it as
.claude/skills/math-derivation/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- math-derivation
- description
- 数学公式与理论线推导。用于整理散乱公式、固定不变量和记号、推导恒等式/近似/局部命题、检查隐藏假设，或把理论笔记变成可审计推导包。
Math Derivation
建立诚实、可检查的推导链；不把解释、近似或数值现象伪装成严格证明。
Position in the Method Map
本 skill 连接“规格与语义”到“演绎验证/定理证明”：它先保持 ProblemContract 的定义和量词不变，再将论证拆成可复核的中间命题。它不是 Lean elaboration，也不是自动化求解器；需要形式化 proof term 时转交 math-formalization。地图总览见 FORMAL-METHODS-MAP.md。
When to Use This Skill
- 用户要求推导公式、整理理论线或解释等式来源。
- 当前公式混用了不同对象、极限、尺度或适用域。
- 需要将全局量分解为可解释项，或从一般模型收敛到可验证特例。
Not For / Boundaries
- CandidateObservation 未形成明确用户目标或 active ProblemContract 时回到
math-discovery；不得用推导文本替候选完成准入。 - 完整定理证明交给
math-proof。 - 具体符号/数值检查交给
math-computation，其结果只是证据层。 - 不静默增加假设、交换极限/积分、忽略收敛条件或改变目标对象。
Quick Reference
Target：要得到什么，角色是 identity / proposition / approximation / interpretation？
Invariant object：贯穿推导的唯一顶层对象是什么？
Assumptions：显式、隐藏、局部、渐近和正则性条件。
Notation：每个符号先定义，一物一名。
Map：中间恒等式/引理、每步所用假设、近似进入位置。
Checks：维度、定义域、边界、极限、特例、符号与数值反算。
Status：coherent / coherent-after-reframing / blocked。Examples
Example 1：精确恒等式
- 输入：需要证明两个代数表达式等价。
- 动作：固定定义域和变量假设，逐步变形，再交给 SymPy 做差为零检查。
- 验收：区分纸面推导与
symbolically-checked，不标记 kernel-checked。
Example 2：渐近近似
- 输入：推导大样本近似。
- 动作：标明极限变量、余项、均匀性和常数依赖。
- 验收：结论含适用域和误差阶，不把近似写成恒等式。
Example 3：目标对象错误
- 输入：局部代理量被当作全局目标。
- 动作：指出对象切换，重构为“全局量 → 分解 → 局部切片”。
- 验收：状态为
coherent-after-reframing并保留原目标差异。
References
references/source-map.md：推导方法来源和未吸收边界。references/pressure-tests.md：隐藏假设压力场景。
Maintenance
- Sources：
kdense-scientific-skills与本项目 ProblemContract/证据分层规则；不依赖未发布本机来源。 - Last updated：2026-08-13。
- Verification：
python3 scripts/smoke_math.py只验证计算层；推导仍需逐步审计。
© tradecatlabs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (references) in research/vibe-mathing-cn-public/.codex/skills/math-derivation of tradecatlabs/vibe-coding-cn.
- SKILL.md
- CHANGELOG.md
- VERSION
- references/index.md
- references/pressure-tests.md
- references/source-map.md
Open the folder on GitHubat commit 0a7fdf4
Compare with similar skills
Math Derivation Auditor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Math Derivation Auditor this skilltradecatlabs/vibe-coding-cn | 17k | — | ~429 | Automated safety check: Pass | MIT | |
| SympyzLanqing/codex-claude-academic-skills | 4.7k | 15 repos | ~3.4k | Automated safety check: Pass | MIT | |
| Edu Analytic Geometrywy51ai/edulab | 1.4k | 1 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Edu Solid Geometrywy51ai/edulab | 1.4k | 1 repos | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Math Toolsananddtyagi/cc-marketplace | 687 | 1 repos | ~1.3k | Automated safety check: Pass | None | |
| Edu Chem Reactionwy51ai/edulab | 1.4k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Edu Analytic Geometry
wy51ai/edulab
把一道解析几何题解成一个自包含的交互教学网页：左栏题面 + 动态控制台（一个 可变参数滑块驱动实时重算的几何量 + 理论范围/定值指示），中栏 KaTeX 分步解析，右栏 2D Canvas 动态几何画板（椭圆/双曲线/抛物线/圆 + 动直线/动点 + 向量 + 标注 + 画笔涂鸦）。
Edu Solid Geometry
wy51ai/edulab
把一道立体几何题解成一个自包含的交互教学网页：左侧 MathJax 分步解析， 右侧 Three.js 可交互 3D 模型（分步高亮 + 镜头切换）。支持三种入口——给定文字题目、 随机出题、上传题目图片识别后解题。覆盖正方体/长方体、棱锥/棱柱、圆柱/圆锥上的线面角、 二面角、异面直线夹角、点到平面距离、体积等题型，统一用"建系+向量法"，并由 sympy 精确 计算驱动（答案、3D…
Math Tools
ananddtyagi/cc-marketplace
Deterministic mathematical computation using SymPy. An agent skill from ananddtyagi/cc-marketplace.
Edu Chem Reaction
wy51ai/edulab
把一个化学反应做成自包含的微观 3D 交互演示网页：左/上为 Three.js 可交互分子动画 （拖滑块看断键·成键·原子重组，分步高亮），右为 KaTeX 反应方程 + 分步讲解 + 原子守恒计数 + 可选能量-反应进程曲线。支持三入口——给定文字反应/方程、随机出题、上传图片识别后演示。
Math
parcadei/Continuous-Claude-v3
Unified math capabilities - computation, solving, and explanation.
More from tradecatlabs/vibe-coding-cn
All 17 skills in this repoAuto Skill Builder
tradecatlabs/vibe-coding-cn
Meta-skill that turns docs, APIs, code or specs into a reusable skill with references and a quality gate, and refactors skills that are unclear or misfire.
Web3 Smart Contract Grep Arsenal
tradecatlabs/vibe-coding-cn
A master set of ten grep command blocks that surface likely vulnerability classes in Solidity source within the first 30 minutes of auditing a new protocol.
Auto tmux Operator
tradecatlabs/vibe-coding-cn
Operates tmux sessions like an administrator: reads pane output, sends keys, inspects many panes at once, and coordinates multiple AI terminals through a swarm state script, built on oh-my-tmux.
Web3 Bug Bounty AI Tools
tradecatlabs/vibe-coding-cn
A selection guide to AI-driven tools for Web3 bug bounty work, from autonomous web pentesters to smart contract bug finders, with notes on authorization.
Ethereum Smart Contract Vulnerability Analysis
tradecatlabs/vibe-coding-cn
Runs Slither and Mythril against Solidity contracts to find reentrancy, overflow and access-control bugs before mainnet deployment, then triages and reports findings.
Math Computation
tradecatlabs/vibe-coding-cn
Runs reproducible math computations and counterexample searches with SymPy, NumPy and mpmath, logging evidence without presenting results as proofs.
Related
Works with
Categories
Questions about Math Derivation Auditor
What does Math Derivation Auditor do?
Constructs honest, checkable derivation chains for formulas and theory notes, and keeps approximations and numerical hints from passing as rigorous proof. The skill sits between problem specification and formal proof. It keeps the definitions and quantifiers of the problem contract fixed, then breaks the argument into intermediate propositions a reviewer can check.
When should I use Math Derivation Auditor?
Math Derivation Auditor fits situations like: tidying scattered formulas into one derivation with fixed notation; checking a derivation for hidden assumptions, mixed objects or changed limits; deriving an asymptotic approximation with its domain of validity and error order.
How do I install Math Derivation Auditor in Claude Code?
Run `npx skills add tradecatlabs/vibe-coding-cn --skill math-derivation -a claude-code`. Or copy the skill folder (research/vibe-mathing-cn-public/.codex/skills/math-derivation in tradecatlabs/vibe-coding-cn) into .claude/skills/math-derivation in your project. Claude Code loads it when a task matches its description.
How do I install Math Derivation Auditor in Codex?
Run `npx skills add tradecatlabs/vibe-coding-cn --skill math-derivation -a codex`. Or copy the skill folder (research/vibe-mathing-cn-public/.codex/skills/math-derivation in tradecatlabs/vibe-coding-cn) into .agents/skills/math-derivation in your project. Codex loads it when a task matches its description.
Can I use Math Derivation Auditor in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tradecatlabs/vibe-coding-cn --skill math-derivation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/math-derivation, .gemini/skills/math-derivation, .github/skills/math-derivation and .opencode/skills/math-derivation in your project.
What does Math Derivation Auditor need to run?
Going by SKILL.md and its folder, Math Derivation Auditor needs the command-line tools its instructions call (python3). Our summary lists: SymPy, if you want the symbolic difference-to-zero check for identities.
Does Math Derivation Auditor access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Math Derivation Auditor safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Math Derivation Auditor use?
Math Derivation Auditor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Math Derivation Auditor use?
About 429 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 190 tokens, read only when the agent opens those files.
What are the alternatives to Math Derivation Auditor?
Skills that share tags, products or a category with Math Derivation Auditor: Sympy (zLanqing/codex-claude-academic-skills, 4.7k stars), Edu Analytic Geometry (wy51ai/edulab, 1.4k stars), Edu Solid Geometry (wy51ai/edulab, 1.4k stars) and Math Tools (ananddtyagi/cc-marketplace, 687 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Math Derivation Auditor?
tradecatlabs (a GitHub user) maintains it in tradecatlabs/vibe-coding-cn, which has 17,300 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 9, 2026.
Source: tradecatlabs/vibe-coding-cn on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.